Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    issues related to function execution and system operation errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    not happening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.53
    CloseOperation
    -0.52
     kasarigan
    -0.52
     Italijani
    -0.52
    abetes
    -0.51
     الرياضيه
    -0.50
    tawesome
    -0.49
     متعلقه
    -0.49
    ]")]
    -0.48
    contentLoaded
    -0.47
    POSITIVE LOGITS
     überhaupt
    0.49
     enough
    0.36
     vůbec
    0.35
     anything
    0.34
     siquiera
    0.34
     any
    0.33
     suficientes
    0.33
     lámina
    0.33
     transfieras
    0.33
     acoper
    0.32
    Act Density 0.097%

    No Known Activations